Part-of-Speech Context Vectors: Approximating Distributional Meaning of Syntactic Category Symbols
Open Access
- 23 June 2026
- journal article
- research article
- Published by MDPI AG in Big Data and Cognitive Computing
- Vol. 10 (7) , 202
Abstract
Words occurring in similar contexts have been observed to have similar meanings. A natural and established method within computational linguistics implements this observation by representing words as vectors with dimensions determined by words that are witnessed in fixed positions in relation to the target word. We generalize this context vector approach to part-of-speech (POS) sequences appropriate to word sequences. As with words, the context of a POS tag (considering the POS tags occurring before and after any target tag) reflects its syntactic constraints and may approximate the “meaning” of the target tag, from a distributional perspective. We use the 111-million-word British National Corpus (BNC) and the sequence of POS labels lifted from those texts to calculate POS context vectors. We observed significant agreement between the clusters of POS context vectors and the supercategories of corresponding POS tags, and examined potential categorization of the POS categories that emerged from the vector clusters. We also found that though vector measures partially align with the predictions of generativist linguistic theories, the approach suggests a more complex relation between syntactic categories. We conclude that a mutual-information-based approach better approximates the distributional “meaning” of syntactic categories than the conditional probability distribution of POS symbols.Keywords
Funding Information
- China Scholarship Council
- Trinity College Dublin
This publication has 59 references indexed in Scilit:
- Complex Networks & Their Applications XII2024
- Understanding the Adjusted Rand Index and Other Partition Comparison Indices Based on Counting Object PairsJournal of Classification, 2022
- Understanding the Rand Index2020
- There is More to Negation than ModalityJournal of Philosophical Logic, 2017
- Vector Space Models of Word Meaning and Phrase Meaning: A SurveyLanguage and Linguistics Compass, 2012
- Principal component analysisWIREs Computational Statistics, 2010
- On Similarity Indices and Correction for Chance AgreementJournal of Classification, 2006
- Kappa coefficients in medical researchStatistics in Medicine, 2002
- A context vector model for information retrievalJournal of the American Society for Information Science and Technology, 2002
- Comparing partitionsJournal of Classification, 1985